Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ingredients list or name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺲ
    0.98
    ﻚ
    0.86
     télévision
    0.86
    ﻒ
    0.85
     créé
    0.84
     instala
    0.84
    お金
    0.84
    ﻄ
    0.84
    ä
    0.83
     slučaj
    0.82
    POSITIVE LOGITS
    x
    1.68
    i
    1.62
    in
    1.61
    re
    1.58
    ل
    1.48
    ir
    1.48
    at
    1.46
     Ingredients
    1.37
    r
    1.36
    al
    1.35
    Act Density 0.015%

    No Known Activations